More about HKUST
Applications of Latent Dirichlet Allocation and Hierarchical Dirichlet Processes
Speaker: Dr. Alice Oh Department of Computer Science Korea Advanced Institute of Science and Technology Title: "Applications of Latent Dirichlet Allocation and Hierarchical Dirichlet Processes" Date: Monday, 14 February 2011 Time: 4:00pm - 5:00pm Venue: Lecture Theatre F (near lifts 25/26), HKUST Abstract: Latent Dirichlet Allocation (LDA) and Hierarchical Dirichlet Processes (HDP) have become popular models for discovering latent semantics from text corpora. I will first start this talk with what LDA and HDP are and how they are used in common text analysis tasks. Then, I will present three recent papers from our research group that extend LDA and HDP to analyze three different text corpora: online reviews, news articles, and conference proceedings. With the online reviews, we propose a variant of LDA called Aspect and Sentiment Unification Model (ASUM) to analyze topics and sentiments jointly in an unsupervised fashion. With the news articles, we use LDA to generate topic chains to model temporal patterns of similar topics. With the conference proceedings, we propose a variant of HDP called distant dependent Chinese Restaurant Franchise (ddCRF) to discover how new topics emerge through time. ********************* Biography: Alice Oh is an Assistant Professor of Computer Science at Korea Advanced Institute of Science and Technology. She leads her research group, Users and Information Lab, with the vision of delivering information to satisfy the user. To that end, she studies and employs methods from machine learning, human-computer interaction, and statistical natural language processing. Alice completed her M.S. in Language and Information Technologies at CMU and her Ph.D. in Computer Science at MIT.